© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1497
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" and its occurrences throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icators
    -0.79
    clud
    -0.71
    sing
    -0.71
     INTO
    -0.71
    idential
    -0.70
    igion
    -0.67
    endas
    -0.66
    rored
    -0.62
    owicz
    -0.62
    icator
    -0.62
    POSITIVE LOGITS
    ��
    0.65
    龍契士
    0.64
    ��
    0.62
    ��
    0.61
     Klux
    0.59
    ��
    0.59
     skelet
    0.58
     demol
    0.57
     Lever
    0.57
    lication
    0.57
    Activations Density 0.058%

    No Known Activations